Foundations 1958
The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain
Frank Rosenblatt · Psychological Review
doi:10.1037/h0042519
In short
Rosenblatt describes a machine built from simple threshold units whose connection strengths change with experience, so that it learns to sort inputs into categories instead of being programmed to. He analyses what such a network can learn and how reliably it generalises to inputs it has not seen.
Why it matters
It is the first learning neural network: the idea that weights, not rules, should hold the knowledge starts here.
Read first
The 3 Field Guide ideas this paper leans on.
Foundations · Landmark Machine Learning Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples. Neural Networks · Landmark Neural Network A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections. Neural Networks · Standard Perceptron The simplest neural network unit, a single-layer binary classifier that inspired modern deep learning.
Nearby papers
Canon · 1986 Learning Representations by Back-Propagating Errors Backpropagation is how essentially every neural network, from LeNet to today’s LLMs, is trained. Canon · 1998 Gradient-Based Learning Applied to Document Recognition It is the blueprint for the convolutional network, the architecture that later cracked computer vision. Canon · 2014 Generative Adversarial Networks GANs launched the modern era of generated images and dominated image synthesis until diffusion arrived. Canon · 2015 Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift It made very deep networks practical to train, and normalization layers became a standard part of the recipe.